ICCV 2019 accepted papers on Graph learning
23 of the 1,075 papers accepted at ICCV 2019 (2.1%) are on Graph learning, compared with 0.3% at ICCV 2017. They fall into 4 topics.
See ICCV 2019 in the interactive map
Submitting to ICCV? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Knowledge and temporal graphs · 14 papers
- STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction (716 citations)
- Graph Convolutional Networks for Temporal Action Localization (573 citations)
- Dynamic Graph Attention for Referring Expression Comprehension (252 citations)
- Graph-Based Object Classification for Neuromorphic Vision Sensing (192 citations)
- Unpaired Image Captioning via Scene Graph Alignments (189 citations)
- Specifying Object Attributes and Relations in Interactive Scene Generation (185 citations)
- Language-Conditioned Graph Networks for Relational Reasoning (166 citations)
- Bayesian Graph Convolution LSTM for Skeleton Based Action Recognition (126 citations)
- DAGMapper: Learning to Map by Discovering Lane Topology (109 citations)
- Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid (97 citations)
- Scene Graph Prediction With Limited Labels (64 citations)
- G3raphGround: Graph-Based Language Grounding (58 citations)
and 2 more in the interactive map.
Graph algorithms and clustering · 4 papers
- Learning Combinatorial Embedding Networks for Deep Graph Matching (244 citations)
- Floor-SP: Inverse CAD for Floorplans by Sequential Room-Wise Shortest Path (104 citations)
- Deep Supervised Hashing With Anchor Graph (66 citations)
- End-to-End Learning for Graph Decomposition (15 citations)
